电力系统文本抽取摘要的层次双向LSTM序列模型

Wei Jiang, Yunfeng Zou, Ting Zhao, Qiang Zhang, Yinglong Ma
{"title":"电力系统文本抽取摘要的层次双向LSTM序列模型","authors":"Wei Jiang, Yunfeng Zou, Ting Zhao, Qiang Zhang, Yinglong Ma","doi":"10.1109/ISCID51228.2020.00071","DOIUrl":null,"url":null,"abstract":"With the increasing volume of documents in electric power systems, it is urgent and necessary for electric power systems managers to efficiently analyze the massive documents and make reasonable decisions by capturing the main points of the document as quickly as possible. The text summarization technique provides a feasible way to efficiently analyze and obtain the main contents residing in the document. In this paper, we present a Hierarchical Bidirectional Long Term Short Memory Sequence model for extractive text summarization in electric power systems in order to efficiently and accurately summarize electric power documents and obtain a summary of the document. Our model is divided into four layers including the embedding layer, the word layer, the sentence layer, and the classification layer in a hierarchical manner. The related experiments were made based on the electric power data set that contains more than 2000 electrical papers, in comparison with the existing approaches based on the CRF, CNN, and RNN models. The experimental results show that the performance based on our approach is superior to the three approaches against the three performance indexes ROUGE-1, ROUGE-2, and ROUGE-L.","PeriodicalId":236797,"journal":{"name":"2020 13th International Symposium on Computational Intelligence and Design (ISCID)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"A Hierarchical Bidirectional LSTM Sequence Model for Extractive Text Summarization in Electric Power Systems\",\"authors\":\"Wei Jiang, Yunfeng Zou, Ting Zhao, Qiang Zhang, Yinglong Ma\",\"doi\":\"10.1109/ISCID51228.2020.00071\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"With the increasing volume of documents in electric power systems, it is urgent and necessary for electric power systems managers to efficiently analyze the massive documents and make reasonable decisions by capturing the main points of the document as quickly as possible. The text summarization technique provides a feasible way to efficiently analyze and obtain the main contents residing in the document. In this paper, we present a Hierarchical Bidirectional Long Term Short Memory Sequence model for extractive text summarization in electric power systems in order to efficiently and accurately summarize electric power documents and obtain a summary of the document. Our model is divided into four layers including the embedding layer, the word layer, the sentence layer, and the classification layer in a hierarchical manner. The related experiments were made based on the electric power data set that contains more than 2000 electrical papers, in comparison with the existing approaches based on the CRF, CNN, and RNN models. The experimental results show that the performance based on our approach is superior to the three approaches against the three performance indexes ROUGE-1, ROUGE-2, and ROUGE-L.\",\"PeriodicalId\":236797,\"journal\":{\"name\":\"2020 13th International Symposium on Computational Intelligence and Design (ISCID)\",\"volume\":\"37 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-12-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2020 13th International Symposium on Computational Intelligence and Design (ISCID)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ISCID51228.2020.00071\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 13th International Symposium on Computational Intelligence and Design (ISCID)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISCID51228.2020.00071","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2

摘要

随着电力系统中文件数量的不断增加,如何对海量文件进行高效的分析,尽快抓住文件的要点,做出合理的决策,是电力系统管理人员迫切需要的。文本摘要技术为有效分析和获取文档中的主要内容提供了一种可行的方法。本文提出了一种用于电力系统文本抽取摘要的分层双向长短期记忆序列模型,以便高效、准确地对电力文档进行摘要。我们的模型分为四层,即嵌入层、词层、句子层和分类层。在包含2000多篇电子论文的电力数据集上进行相关实验,并与现有基于CRF、CNN和RNN模型的方法进行比较。实验结果表明,在ROUGE-1, ROUGE-2和ROUGE-L三个性能指标上,基于我们的方法的性能优于三种方法。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
A Hierarchical Bidirectional LSTM Sequence Model for Extractive Text Summarization in Electric Power Systems
With the increasing volume of documents in electric power systems, it is urgent and necessary for electric power systems managers to efficiently analyze the massive documents and make reasonable decisions by capturing the main points of the document as quickly as possible. The text summarization technique provides a feasible way to efficiently analyze and obtain the main contents residing in the document. In this paper, we present a Hierarchical Bidirectional Long Term Short Memory Sequence model for extractive text summarization in electric power systems in order to efficiently and accurately summarize electric power documents and obtain a summary of the document. Our model is divided into four layers including the embedding layer, the word layer, the sentence layer, and the classification layer in a hierarchical manner. The related experiments were made based on the electric power data set that contains more than 2000 electrical papers, in comparison with the existing approaches based on the CRF, CNN, and RNN models. The experimental results show that the performance based on our approach is superior to the three approaches against the three performance indexes ROUGE-1, ROUGE-2, and ROUGE-L.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信